INDEX

Explanations

visual imagery related to spatial positioning or physical placement

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ujednoznacz

-0.70

 kaarangay

-0.64

 uintptr

-0.59

RenderAtEndOf

-0.57

 الحره

-0.55

 Olímpicos

-0.54

تقاوى

-0.54

reathe

-0.53

 старости

-0.52

POSITIVE LOGITS

 ground

1.69

 floor

1.57

ground

1.41

floor

1.24

 GROUND

1.24

Ground

1.22

 Ground

1.20

 floors

1.18

 pavement

1.18

 Floor

1.15

Activations Density 0.213%

visual imagery related to spatial positioning or physical placement

No Comments

No Known Activations